Change Healthcare Unveils Social Determinants of Health Analytics Solution

Change Healthcare Acquires Credentialing Tech Docufill to Improve Administrative Efficiency

What You Should Know:

– Change Healthcare launches national data resource on
social determinants of health (SDoH) for doctors, insurers and life sciences
organizations to better understand the connection between where a person lives
and how they live their life to the care a patient receives and their health
outcome.

– 80% of U.S. health outcomes are tied to a patient’s
social and economic situation, ranging from food, housing, and transportation
insecurity to ethnicity.


Change Healthcare, today announced the launch of Social Determinants of Health (SDoH) Analytics solution that will serve as an innovative national data resource that connects the circumstances of people’s lives to the care they receive. The SDoH Analytics solution is designed for health systems, insurers, and life sciences organizations to explore how geodemographic factors affect patient outcomes.


Understanding Social Determinants of Health

SDoH includes factors such as socioeconomic status, education, demographics, employment, health behaviors, social support networks, and access to healthcare. Individuals who experience challenges in any of these areas can face significant risks to their overall health.

“All the work I do—for Mayo Clinic, the COVID-19 Healthcare Coalition, and The Fight Is In Us— is predicated on equity,” said John Halamka, president, Mayo Clinic Platform. “The only way we can eliminate racism and disparities in care is to better understand the challenges. Creating a national data resource on the social determinants of health is an impactful first step.”

The SDoH Portrait Analysis includes financial attributes, education
attributes, housing attributes, ethnicity, and health behavior attributes.

3 Ways Healthcare Organizations Can Leverage SDoH
Analytics

Healthcare organizations can now use SDoH Analytics to
assess, select, and implement effective programs to help reduce costs and
improve patient outcomes. Organizations can choose one of three ways to use
SDOH Analytics:

1. Receive customized reports identifying SDoH factors that
impact emergency room, inpatient, and outpatient visits across diverse
population health segments.

2. Append existing systems with SDoH data to close
information gaps and help optimize both patient engagement and outcomes.

3. Leverage a secure, hosted environment with ongoing
compliance monitoring for the development of unique data analytics, models, or
algorithms.

Why It Matters

Scientific research has shown that 80% of health outcomes
are SDoH-related. Barriers such as food and housing availability,
transportation insecurity, and education inequity must be addressed to reduce
health disparities and improve outcomes. Change Healthcare’s SDoH Analytics
links deidentified claims with factors such as financial stability, education
level, ethnicity, housing status, and household characteristics to reveal the
correlations between SDoH, clinical care, and patient outcomes. The resulting
dataset is de-identified in accordance with HIPAA privacy regulations.

“Health systems, insurers, and scientists can now use SDoH Analytics to make a direct connection between life’s circumstances and health outcomes,” said Tim Suther, senior vice president of Data Solutions at Change Healthcare. “This helps optimize healthcare utilization, member engagement, and employer wellness programs. Medical affairs and research are transformed. And most importantly, patient outcomes improve. SDoH Analytics makes these data-driven insights affordable and actionable.”

NVIDIA Develops AI Model to Accurately Predict Oxygen Needs for COVID-19 Patients

NVIDIA Develops AI Model to Accurately Predict Oxygen Needs for COVID-19 Patients

What You Should Know:

– NVIDIA and Massachusetts General Brigham Hospital
researchers develop an AI model that determines whether a person showing up in
the emergency room with COVID-19 symptoms will need supplemental oxygen hours
or even days after an initial exam.

– The ultimate goal of this model is to predict the
likelihood that a person showing up in the emergency room will need
supplemental oxygen, which can aid physicians in determining the appropriate
level of care for patients, including ICU placement.


Researchers at NVIDIA
and Massachusetts General Brigham
Hospital
have developed an artificial
intelligence (AI)
model that determines whether a person showing up in the
emergency room with COVID-19
symptoms will need supplemental oxygen hours or even days after an initial
exam.

The original AI model, named CORISK, was developed by scientist Dr. Quanzheng Li at Mass General Brigham. It combines medical imaging and health records to help clinicians more effectively manage hospitalizations at a time when many countries may start seeing the second wave of COVID-19 patients.

EXAM (EMR CXR AI Model) & Results

To develop an AI model that doctors trust and that
generalizes to as many hospitals as possible, NVIDIA and Mass General Brigham
embarked on an initiative called EXAM (EMR CXR AI Model) the largest,
most diverse federated
learning
 initiative with 20 hospitals from around the world.

In just two weeks, the global collaboration achieved a model
with .94 area under the curve (with an AUC goal of 1.0), resulting in excellent
prediction for the level of oxygen required by incoming patients. The federated
learning model will be released as part of NVIDIA
Clara on NGC
 in the coming weeks.

Leveraging NVIDIA’s Clara Federated Learning Framework

Using NVIDIA Clara
Federated Learning Framework
, researchers at individual hospitals were able
to use a chest X-ray, patient vitals and lab values to train a local model and
share only a subset of model weights back with the global model in a
privacy-preserving technique called federated learning.

The ultimate goal of this model is to predict the likelihood
that a person showing up in the emergency room will need supplemental oxygen,
which can aid physicians in determining the appropriate level of care for
patients, including ICU placement.

Dr. Ittai Dayan, who leads the development and deployment of AI at Mass General Brigham, co-led the EXAM initiative with NVIDIA and facilitated the use of CORISK as the starting point for the federated learning training. The improvements were achieved by training the model on distributed data from a multinational, diverse dataset of patients across North and South America, Canada, Europe, and Asia.

Participating Hospitals in EXAM Initiative

In addition to Mass Gen Brigham and its affiliated
hospitals, other participants included: Children’s National Hospital in Washington,
D.C.; NIHR Cambridge Biomedical Research Centre; The Self-Defense Forces
Central Hospital in Tokyo; National Taiwan University MeDA Lab and MAHC and
Taiwan National Health Insurance Administration; Kyungpook National
University Hospital in South Korea; Faculty of Medicine, Chulalongkorn
University in Thailand; Diagnosticos da America SA in Brazil; University of
California, San Francisco; VA San Diego; University of Toronto; National
Institutes of Health in Bethesda, Maryland; University of Wisconsin-Madison
School of Medicine and Public Health; Memorial Sloan Kettering Cancer Center in
New York; and Mount Sinai Health System in New York.

Each of these hospitals used NVIDIA Clara to
train its local models and participate in EXAM. Rather than needing to pool
patient chest X-rays and other confidential information into a single location,
each institution uses a secure, in-house server for its data. A separate
server, hosted on AWS, holds the global deep neural network, and each
participating hospital gets a copy of the model to train on its own dataset.

NVIDIA Announces Partnership with GSK’s AI-Powered Lab
for Discovery of Medicines and Vaccines

In addition, the new AI model, NVIDIA today announced a
partnership with global healthcare company GSK and its AI group, which is
applying computation to the drug and vaccine discovery process. GSK has
recently established a new London-based AI hub, one of the first of its kind,
which will leverage GSK’s significant genetic and genomic data to improve the
process of designing and developing transformational medicines and vaccines.

Located in London’s rapidly growing Knowledge Quarter, GSK’s hub will utilize biomedical data, AI methods, and advanced computing platforms to unlock genetic and clinical data with increased precision and scale. The GSK AI hub, once fully operational, will be home to its U.K.-based AI team, including GSK AI Fellows, a new professional training program, and now scientists from NVIDIA.


NVIDIA Building UK’s Most Powerful Supercomputer,
Dedicated to AI Research in Healthcare

NVIDIA Building UK’s Most Powerful Supercomputer, Dedicated to AI Research in Healthcare

NVIDIA today announced that it is building the United
Kingdom’s most powerful supercomputer, which it will make available to U.K.
healthcare researchers using AI to solve pressing medical challenges, including
those presented by COVID-19.

Expected to come online by year end, the “Cambridge-1”
supercomputer will be an NVIDIA DGX SuperPOD™ system capable of delivering more
than 400 petaflops of AI performance and 8 petaflops of Linpack performance,
which would rank it No. 29 on the latest TOP500 list of the world’s most powerful
supercomputers. It will also rank among the world’s top 3 most energy-efficient
supercomputers on the current Green500 list.

Sonde Health Acquires NeuroLex Lab’s Voice-Based Survey Platform

Sonde Health Acquires NeuroLex’s Voice-Based Survey Platform

What You Should Know:

– Sonde Health acquires NeuroLex Laboratories, Inc. to forms
one of the world’s preeminent biobanks focused on vocal biomarkers.

– NeuroLex’s core product, SurveyLex, makes it easy to
create and distribute voice surveys in less than a minute as URL links through
web browsers.


Sonde Health, a
Boston-based digital vocal biomarker technology platform announced it has acquired
NeuroLex Laboratories, Inc., a leading
voice-enabled survey and data acquisition platform. The
acquisition brings together two of the leading forces in the vocal biomarker
space.

Sonde will acquire NeuroLex’s popular web-enabled voice
survey and analysis platform, as well as its rich dataset, which when combined
with Sonde’s leading voice-based dataset, forms one of the world’s preeminent
biobanks focused on vocal biomarkers. In addition, merging Sonde’s mobile and
voice-assistant platforms with NeuroLex’s web-based capabilities will enable
the delivery of voice-enabled heath detection and monitoring over any platform.

Democratizing Voice Computing

Over the past two years, NeuroLex has built one of the
largest laboratories in the world to collect, label, and model voice data
tagged with health conditions comprised of over 40 research fellows across 12
universities that have published over 5 peer-reviewed journal articles.
NeuroLex’s core product, SurveyLex, makes it easy to create and distribute
voice surveys in less than a minute as URL links through web browsers. With
this product, NeuroLex has curated a biobank comprised of over 500,000 voice samples
from over 30,000 individuals alongside a host of pharmaceutical and academic
partners. 

Acquisition
Benefits for Sonde

“At Sonde, we have unlocked voice as a new vital sign to enable secure, accessible, and non-intrusive monitoring of health. Incorporating NeuroLex’s impressive work in voice-based surveys and research moves us significantly forward in becoming the one-stop shop for health condition detection and monitoring through voice,” said David Liu, CEO of Sonde Health. “NeuroLex’s voice-based survey platform and biobank will accelerate our research and development, and our collection and analysis of high-quality voice data, bolstering all the products we provide to our customers.”

Sonde’s proprietary technology works by sensing and
analyzing subtle changes in the voice due to changes in a person’s physiology.
The company’s respiratory and depression health checks are available
today. 

As part of the acquisition, Jim Schwoebel, the chief executive
officer of NeuroLex, will join Sonde’s leadership team as Vice President, Data
and Research.

“I am thrilled to bring Jim and his team on board,” continued Liu. “His experience in building NeuroLex, shared mission of using vocal biomarkers to move healthcare forward, and expertise in building large voice-based datasets and machine learning make Jim a tremendous addition to the Sonde team.”

Financial details of the acquisition were not disclosed.

Eko Awarded $2.7M NIH Grant for Heart Murmur & Valvular Heart Disease Detection Algorithms

FDA Breakthrough Status Granted for Heart Failure Algorithm by Eko

What You Should Know:

– The National Institutes of Health (NIH) has granted next-generation
cardiac AI company Eko an award totaling $2.7 million to support continued
collaborative work with Northwestern Medicine Bluhm Cardiovascular Institute

– The grant will focus on validating algorithms and help
more accurately screen for heart murmurs and valvular heart disease during
routine office visits with Northwestern Medicine.

– By incorporating data from tens of thousands of heart
patterns into Eko sensors and algorithms, clinicians will have
cardiologist-level precision in detecting subtle abnormalities from normal
sounds.


Eko, a digital health company
building AI-powered screening
and telehealth solutions to
fight cardiovascular disease, today announced it has been awarded a $2.7
million Small Business Innovation Research (SBIR) grant by the National
Institutes of Health (NIH). The grant will fund the continued collaborative
work with Northwestern Medicine Bluhm Cardiovascular Institute to validate
algorithms that help providers screen for pathologic heart murmurs and valvular
heart disease during routine office visits.

Eko and Northwestern first announced their collaboration in
March 2019 to provide a simpler, lower-cost way for clinicians to identify
patients with heart disease without the use of screening tools such as
echocardiograms which are typically only available at specialty clinics. By
incorporating data from tens of thousands of heart patterns into the
stethoscope and its algorithms, clinicians will have cardiologist-level
precision in detecting subtle abnormalities from normal sounds.

“Cardiovascular disease is the leading cause of death in the U.S., and valvular heart disease often goes undetected because of the challenge of hearing murmurs with traditional stethoscopes, particularly in noisy or busy environments. A highly accurate clinical decision support algorithm that is able to detect and classify valvular heart disease will help improve accuracy of diagnosis and the detection of potential cardiac abnormalities at the earliest possible time, allowing for timely intervention,” said James D. Thomas, MD, director of the Center for Heart Valve Disease at Northwestern Medicine and the clinical study’s principal investigator. “Our work with Eko aspires to extend the auscultatory expertise of cardiologists to more general practitioners to better serve our patient community, playing a pivotal role in growing the future of cardiovascular medicine.”

Recent FDA Clearance and Telehealth Platform Launch

This recognition comes on the heels of several key company
milestones, including the clearance
of Eko’s cardiac AI algorithms by the U.S. Food and Drug Administration and the
launch
of Eko’s AI-powered telehealth
platform. Eko’s ECG-based deep learning algorithm, developed on a large
clinical dataset in collaboration with the Mayo Clinic, can help efficiently
identify signs of possible heart failure in patients.

Eko’s AI-Powered telehealth platform for virtual pulmonary and cardiac exams, providing clinicians within-person level exam capabilities during video visits. The platform is already deployed by more than 200 health systems for telehealth, the platform goes beyond standard video conferencing to facilitate stethoscope audio, ECG live-streaming, and FDA-cleared identification of atrial fibrillation (AFib) and heart murmurs.